8 papers
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
Silin Gao, Hao Zhao, Zeming Chen +8
Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences. Such inputs require models to predict or simulate multi…
PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors
Jiaxin Yang, Yu Hou, Muxin Liu +5
Can general-purpose image editors predict physical maps from a single RGB image? General-purpose image editors differ from standard task-specific dense-prediction models: they do n…
Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
Badr AlKhamissi, C. Nicolò De Sabbata, Greta Tuckute +3
Human cognitive behavior arises from the interaction of specialized brain networks dedicated to distinct functions, such as language, logic, and social reasoning. Inspired by this…
Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
Yiyang Feng, Zeming Chen, Haotian Wu +2
A common solution for mitigating outdated or incorrect information in Large Language Models (LLMs) is to provide updated facts in-context or through knowledge editing. However, the…
PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning
Zeming Chen, Angelika Romanou, Gail Weiss +1
Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode cont…
GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration
Li Mi, Manon Bechaz, Zeming Chen +2
Active Geo-localization (AGL) is the task of localizing a goal, represented in various modalities (e.g., aerial images, ground-level images, or text), within a predefined search ar…